© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 185450
    Prev
    Next
    INDEX
    Explanations

    Balcony, original voltage, politics

    np_acts-logits-general · gemini-2.5-flash-lite

    logical, fervent, Indirect

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     لتح
    0.50
    MaxValue
    0.48
    <unused59>
    0.47
    સિંહ
    0.46
    MiddleLine
    0.46
    வத
    0.46
    اذ
    0.45
    ระหว่าง
    0.45
    сик
    0.45
    IGATION
    0.45
    POSITIVE LOGITS
     (
    0.57
    antly
    0.46
    ¦
    0.44
    П
    0.43
    ■
    0.43
     ■
    0.42
    ‒
    0.42
     rallies
    0.42
    ®
    0.42
     q
    0.41
    Activations Density 0.001%

    No Known Activations